Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the functional effects (key recoverability, free tier restored at 50 calls/day), the failure mode ('If the email can't be accepted, the key keeps working'), the negative consequence of fake emails (key becomes unrecoverable), the consent constraint on marketing, and even the honest caveat that the durability benefit is UNPROVEN with a 0-of-3 cohort. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loading is strong — the ★ heading and the first sentence deliver the core scope. However, the roughly 400-word description is a dense stream of consciousness mixing cohort evidence, pricing tiers, consent policy, and digest marketing into one paragraph. Most sentences earn their place, but the lack of sectioning hurts scannability for an agent trying to extract the key decision rules quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with consent implications, failure modes, tier-gating, and 3 parameters, the description covers everything: when to call, prerequisites (human-shared email), effects, failure behavior, consent requirements, and return value ('Returns the unlocked benefits + confirmation'). The output schema exists, so the return format is already structured; nothing an agent needs to invoke correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds consequence-level meaning beyond the schema: invented or placeholder emails are rejected server-side and make the key unrecoverable, omitting api_key binds the session-active key, and marketing_opt_in must follow explicit human agreement with an unsubscribe guarantee. This is genuinely additive, though it stops short of specifying email format validation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Tie your DC Hub key to your human's email so the key is RECOVERABLE.' It goes further than most by explicitly stating what it does not do ('does NOT make your identity durable') and contrasts itself with the OAuth path, making differentiation from siblings like recover_my_key, claim_free_key, and subscribe_digest immediate without opening their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Call conditions are explicit: 'Call this once your human shares their email' and 'If your human hasn't shared an email, ask them first — don't call this tool with a made-up value.' It names the alternative (OAuth sign-in) with the exact condition that selects it (401 WWW-Authenticate challenge), and provides a concrete PAUSE-and-ask script for the tier-gate scenario.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.